© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39383
    Prev
    Next
    INDEX
    Explanations

    verbs followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.52
    kém
    -1.17
     demanding
    -1.13
     restric
    -1.12
     함께
    -1.09
    怎麼
    -1.09
    一起来
    -1.05
     गणना
    -1.03
     conflic
    -1.02
    嬉しいです
    -1.02
    POSITIVE LOGITS
    onians
    1.22
    größ
    1.22
    "=
    1.16
    ophobic
    1.13
     still
    1.13
    nological
    1.13
    SetBool
    1.12
    ского
    1.10
     their
    1.10
    different
    1.09
    Activations Density 0.082%

    No Known Activations